jeremy
@jerhadf
helping grow more claudes @AnthropicAI
personal views only
๊ฐ์
January 2014
1.6K ํ๋ก์ ์ค 4.2K ํฌ
Opus 5 has a better FrontierCode score at medium effort than higher effort - despite increasing performance with effort on other evals. Why? ๐งต
์ธ๊ธฐ ์๋ ์ฌ์ฉ์
